And what is the local weather zone equivalent of a census tract? Something smaller than a zip code that is somewhat stable in size for the past few years.
https://t.co/0ef8PmEGQp offers city boundaries, but census tract layer loses the city boundaries, so I select the census tracts by eyeball. I know the mapping is not 1:1, but there has to be a better way to obtain census tract values within a city, right? #rstats@kyle_e_walker
Trying to order levels in a #polars categorical was surprising challenging. Spoiler: You need to cast as Enum in polars 1.5.0 #pythonprogramming#Python#polars
Our book Python Polars: The Definitive Guide now has a website: https://t.co/FJ1OjAVwkF. There isn't much to see yet, but you can sign up to get notified when the book is out. ✍
You have 10000 coins. 9999 of them are fair; one is rigged so that it always lands on heads. You choose a coin at random and flip it 10 times; it’s heads all ten times. The coin is probably
What about NHST setup makes any sense in the context of an A/B test? Additionally it's quite far from an actual randomized experiment.
If anything A/B testing more closely resembles continuous optimization. "Statistical significance" is the absolutely the wrong framing for what is an basically a classic exploitation/exploration problem.
New book up!
https://t.co/YqDBLSv16i
This is the #rstan sibling to my #brms translation of @rlmcelreath's 2nd edition. This 0.0.1 version has drafts of Chapters 1 through 8.
1/5
If you have ever participated in an internal data bootcamp lead by your company ... what aspects did you find particularly useful vs useless? #rstats#Python